Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    biological lists with fungi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uoj
    0.52
    arynx
    0.52
    पूर्ति
    0.51
    }^
    0.50
     Fruits
    0.50
    uah
    0.50
    u
    0.49
    aloko
    0.49
    ，$
    0.49
    uestros
    0.48
    POSITIVE LOGITS
    ње
    0.71
     indipendente
    0.68
     Ле
    0.67
    :
    0.66
    ль
    0.64
     estran
    0.63
     can
    0.63
    ление
    0.61
     novices
    0.60
    н
    0.60
    Act Density 0.001%

    No Known Activations